Analysis of Speaker Verification Method Based on Hidden Markov Models for Continuous Speech System

Mahdi Fadil Khaleel

doi:10.26706/ijaefea.4.10.20231904

Analysis of Speaker Verification Method Based on Hidden Markov Models for Continuous Speech System

Mahdi Fadil Khaleeland
International Journal of Analytical, Experimental and Finite Element Analysis
Volume 10: Issue 4, December 2023, pp 119-125

Author's Information

Mahdi Fadil Khaleel

Corresponding Author

Community Health Techniqes Department, Kirkuk Technical Institute, Northern Technical University, Iraq.

mahdi.fadil@ntu.edu.iq

Article -- Peer Reviewed

Published online – 30 December 2023

Open Access article under Creative Commons License

Cite this article – Mahdi Fadil Khaleel, Seong-Won Seo, Gu-Sung Kim, “Analysis of Speaker Verification Method Based on Hidden Markov Models for Continuous Speech System”, International Journal of Analytical, Experimental and Finite Element Analysis, RAME Publishers, vol. 10, Issue 4, pp. 119-125, December 2023.

https://doi.org/10.26706/ijaefea.4.10.20231904

Abstract:-

This paper aim to the effectiveness of speaker verification using prompted text. The progress and enhancement of ASV applications have significant implications, particularly considering their advantages in comparison to alternative biometric methodologies., support vector machines (SVM), Hidden Markov models (HMM), the generalized method of moments (GMM), artificial neural networks (ANN), and combination models are only some of the statistical models used by modern speaker recognition systems‎. Using a dataset collected in Turkish. The goal of this work was to create a continuous speech system using Hidden Markov Models (HMM) on a single mixed monophonic level, independent of any surrounding environment.‎ Subsequently, appropriate speech data is used in the construction of both the client and world models. The text-dependent speaker verification method employs sentence Hidden Markov Models (HMMs) that have been concatenated for the designated text in order to authenticate speakers. The normalized log-likelihood is calculated in the verification stage by comparing the log-likelihood of the client model, which is derived using the Viterbi method and the world model. It is by subtracting these two log-likelihood values that we arrive at the normalized log-likelihood. Finally, a method for evaluating verification results is shown.

Index Terms:-

Text dependent, Turkish data set, Viterbi algorithm, Generalized method of moments.

REFERENCES

Zeinali, H., Sameti, H., & Burget, L. (2017). Text-dependent speaker verification based on i-vectors, neural networks and hidden Markov models. Computer Speech & Language, 46, 53-71.

Zeinali, H., Sameti, H., & Burget, L. (2017). HMM-based phrase-independent i-vector extractor for text-dependent speaker verification. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 25(7), 1421-1435.

Petrovska-Delacrétaz, D., & Khemiri, H. (2017, February). Unsupervised Data-driven Hidden Markov Modeling for Text-dependent Speaker Verification. In International Conference on Pattern Recognition Applications and Methods (Vol. 2, pp. 199-207). Scitepress.

Olsson, J. (2002). Text dependent speaker verification with a hybrid HMM/ANN system. MASTER These Signal processing group, Uppsala University.

Kadhim, I. B., Nasret, A. N., & Mahmood, Z. S. (2022). Enhancement and modification of automatic speaker verification by utilizing hidden Markov model. Indonesian Journal of Electrical Engineering and Computer Science, 27(3), 1397-1403.

Hassan, M. D., Nasret, A. N., Baker, M. R., & Mahmood, Z. S. (2021). Enhancement automatic speech recognition by deep neural networks. Periodicals of Engineering and Natural Sciences, 9(4), 921-927.

Nasret, A. N., Noori, A. B., Mohammed, A. A., & Mahmood, Z. S. (2021). Design of automatic speech recognition in noisy environments enhancement and modification. Periodicals of Engineering and Natural Sciences, 10(1), 71-77.

Gemello, R., Mana, F., & Mori, R. D. (2005). Non-linear estimation of voice activity to improve automatic recognition of noisy speech. In Ninth European Conference on Speech Communication and Technology.

Shahina, A., Yegnanarayana, B., & Kesheorey, M. R. (2004, October). Throat microphone signal for speaker recognition. In Proceedings of ICSLP.

Aibinu, A. M., Salami, M. J. E., & Shafie, A. A. (2012). Artificial neural network based autoregressive modeling technique with application in voice activity detection. Engineering Applications of Artificial Intelligence, 25(6), 1265-1276.

Kepuska, V. Z. (1991). Neural networks for speech recognition applications.

Amrouche, A., Debyeche, M., Taleb-Ahmed, A., Rouvaen, J. M., & Yagoub, M. C. (2010). An efficient speech recognition system in adverse conditions using the nonparametric regression. Engineering Applications of Artificial Intelligence, 23(1), 85-94.

Renals, S., McKelvie, D., & McInnes, F. (1991, April). A comparative study of continuous speech recognition using neural networks and hidden Markov models. In Acoustics, Speech, and Signal Processing, IEEE International Conference on (pp. 369-372). IEEE Computer Society.

Karray, L., & Martin, A. (2003). Towards improving speech detection robustness for speech recognition in adverse conditions. Speech Communication, 40(3), 261-276.